LLM deobfuscation of binaries to pseudocode depends more on reasoning ability and task-specific fine-tuning than on model size, with reasoning models showing robustness across ISAs and obfuscation levels on the new BinDeObfBench.
Binary code summarization: Benchmarking chatgpt/gpt- 4 and other large language models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
REBench is a new benchmark that consolidates existing datasets into a large collection of binaries with knowledge-base-driven ground truth to enable fair LLM evaluation on stripped-binary type and name recovery.
ByteTR recovers variable types in binary code more effectively than prior methods by decoupling unbalanced type sets, mitigating compiler optimization effects via static analysis, and modeling inter-procedural data flows with a gated GNN.
RETROFIT enables continual learning for malware detection and binary summarization by retrospective-free parameter merging with low-rank sparse updates and confidence-guided arbitration, improving retention and generalization without historical data.
ICL4Decomp applies in-context learning to guide LLMs in generating re-executable decompiled code from binaries, reporting roughly 40% higher re-executability than prior methods across datasets and optimization levels.
citing papers explorer
-
Can LLMs Deobfuscate Binary Code? A Systematic Analysis of Large Language Models into Pseudocode Deobfuscation
LLM deobfuscation of binaries to pseudocode depends more on reasoning ability and task-specific fine-tuning than on model size, with reasoning models showing robustness across ISAs and obfuscation levels on the new BinDeObfBench.
-
REBENCH: A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped-Binary Types and Names (Extended Version)
REBench is a new benchmark that consolidates existing datasets into a large collection of binaries with knowledge-base-driven ground truth to enable fair LLM evaluation on stripped-binary type and name recovery.
-
Beyond the Edge of Function: Unraveling the Patterns of Type Recovery in Binary Code
ByteTR recovers variable types in binary code more effectively than prior methods by decoupling unbalanced type sets, mitigating compiler optimization effects via static analysis, and modeling inter-procedural data flows with a gated GNN.
-
Retrofit: Continual Learning with Controlled Forgetting for Binary Security Detection and Analysis
RETROFIT enables continual learning for malware detection and binary summarization by retrospective-free parameter merging with low-rank sparse updates and confidence-guided arbitration, improving retention and generalization without historical data.
-
Context-Guided Decompilation: A Step Towards Re-executability
ICL4Decomp applies in-context learning to guide LLMs in generating re-executable decompiled code from binaries, reporting roughly 40% higher re-executability than prior methods across datasets and optimization levels.